Part of my <a target="_blank" rel="ugc" href="https://civarchive.com/tag/faces%20by%20thegipper">facial expressions</a> series. All of these LoRAs are designed to mesh well with each other and have low impact on your image framing.It's important to face your fears, or at least be able to put a face to them. Jan 18, 2024 Update: It was pretty clear that this model wasn't trained as well as <a rel="ugc" href="https://civarchive.com/images/5580133">the other core expressions</a>, and didn't mix as well, so v2 is <a rel="ugc" href="https://civarchive.com/images/5641654">normalized much better</a> but you may need to prompt it harder. It should be pretty much SFW out of the box, and degrade images less, but I imagine some people might still like v1 better for some of their images.Using the LoRAIt has a hard time working well without hiresfix if the face isn't a prominent part of the framing, so try running with hiresfix if you aren't seeing the face reflect the expression. Check out the gallery for examplesNon-trained words like "wide eyed" work really well. As with my other expression LoRA's I recommend adding strength to the prompt words and not the LoRA weight.Starter prompts:&lt;subject&gt;, scared&lt;subject&gt; &lt;context&gt; BREAK scared expression

Files with SHA256: cacc94f04023633609c52fdb6f55b9d49ce1e174f00f02f1739db1a2e2579ff0